22 free tools for working with LLMs — token and cost estimation, prompt engineering, structured output schemas, and RAG/embedding planning. All client-side, no API key required.
Estimate token counts and API cost across LLM providers.
Visualize Byte-Pair Encoding token boundaries and character breakdown.
See how much of a model's context window your prompt uses.
Compose few-shot prompt pairs and monitor token budget allocation.
Compare prompt versions with token and cost impact.
Cut filler and whitespace to reduce prompt token count.
Build a structured system prompt from role, tone, and constraints.
Generate realistic mock data payloads from JSON Schemas.
Generate Zod or Pydantic schemas from sample JSON.
Build OpenAI and Anthropic tool-calling JSON schemas.
Convert OpenAI/Anthropic tool schemas to OpenAPI 3.1 specifications.
Validate JSON against a JSON Schema, with per-field error paths.
Estimate vector RAM, HNSW graph overhead, and storage cost.
Visualize text chunking boundaries, token counts, and overlapping segments.
Estimate embedding and vector storage cost for RAG.
Preview how a document splits under different chunking strategies.
Model AI SaaS unit economics, token costs, and gross margins across models.
Project the cost of a multi-step agent loop with retries.
Sortable price and context-window comparison across LLMs.
Model Time-to-First-Token (TTFT), streaming speed, and agent latency.
Size GPU VRAM requirements for LoRA, QLoRA, and Full Fine-Tuning across LLMs.
22 tools for the parts of building with LLMs that don't need a model call themselves — estimating token cost, comparing prompt versions, generating structured-output schemas, simulating RAG chunking, and catching sensitive data before it gets pasted into a chat window. Everything runs in your browser; no API keys, no data leaves your machine.